Search results for: deep learning methods

Authors: Zhiyan Meng, Dan Liu, Jintao Meng

Abstract:

Dependable encrypted traffic classification is crucial for improving cybersecurity and handling the growing amount of data. Large language models have shown that learning from large datasets can be effective, making pre-trained methods for encrypted traffic classification popular. However, attention-based pre-trained methods face two main issues: their large neural parameters are not suitable for low-computation environments like mobile devices and real-time applications, and they often overfit by getting stuck in local minima. To address these issues, we developed a lightweight transformer model, which reduces the computational parameters through lightweight vocabulary construction and Squeeze-and-Excitation Block. We use sharpness-aware optimization to avoid local minima during pre-training and capture temporal features with relative positional embeddings. Our approach keeps the model's classification accuracy high for downstream tasks. We conducted experiments on four datasets -USTC-TFC2016, VPN 2016, Tor 2016, and CICIOT 2022. Even with fewer than 18 million parameters, our method achieves classification results similar to methods with ten times as many parameters.

Keywords: sharpness-aware optimization, encrypted traffic classification, squeeze-and-excitation block, pretrained model

Procedia PDF Downloads 15

Authors: Wiem Zemzem, Moncef Tagina

Abstract:

In this work, we are addressing the problem of an autonomous mobile robot navigating in a large, unknown and dynamic environment using reinforcement learning abilities. This problem is principally related to the exploration/exploitation dilemma, especially the need to find a solution letting the robot detect the environmental change and also learn in order to adapt to the new environmental form without ignoring knowledge already acquired. Firstly, a new action selection strategy, called ε-greedy-MPA (the ε-greedy policy favoring the most promising actions) is proposed. Unlike existing exploration/exploitation policies (EEPs) such as ε-greedy and Boltzmann, the new EEP doesn’t only rely on the information of the actual state but also uses those of the eventual next states. Secondly, as the environment is large, an exploration favoring least recently visited states is added to the proposed EEP in order to accelerate learning. Finally, various simulations with ball-catching problem have been conducted to evaluate the ε-greedy-MPA policy. The results of simulated experiments show that combining this policy with the Qlearning method is more effective and efficient compared with the ε-greedy policy in stationary environments and the utility-based reinforcement learning approach in non stationary environments.

Keywords: autonomous mobile robot, exploration/ exploitation policy, large, dynamic environment, reinforcement learning

Procedia PDF Downloads 412

Authors: Atuhurra Jesse, N'guessan Yves-Roland Douha, Pabitra Lenka

Abstract:

The detection of diseases within plants has attracted a lot of attention from computer vision enthusiasts. Despite the progress made to detect diseases in many plants, there remains a research gap to train image classifiers to detect the cacao swollen shoot virus disease or CSSVD for short, pertinent to cacao plants. This gap has mainly been due to the unavailability of high quality labeled training data. Moreover, institutions have been hesitant to share their data related to CSSVD. To fill these gaps, image classifiers to detect CSSVD-infected cacao plants are presented in this study. The classifiers are based on VGG16, ResNet50 and Vision Transformer (ViT). The image classifiers are evaluated on a recently released and publicly accessible KaraAgroAI Cocoa dataset. The best performing image classifier, based on ResNet50, achieves 95.39\% precision, 93.75\% recall, 94.34\% F1-score and 94\% accuracy on only 20 epochs. There is a +9.75\% improvement in recall when compared to previous works. These results indicate that the image classifiers learn to identify cacao plants infected with CSSVD.

Keywords: CSSVD, image classification, ResNet50, vision transformer, KaraAgroAI cocoa dataset

Procedia PDF Downloads 95

Authors: Yi Ding

Abstract:

With the rapid development of educational technologies, higher education institutions are facing the challenge of creating an inclusive learning environment for students from diverse backgrounds. Academic libraries, the hubs of research, instruction, and innovation at higher educational institutions, are facing the same challenge. While academic librarians worldwide have been working hard to provide services for emerging information technology such as information literacy education, online learning support, and scholarly communication advocacy, the problem of digital exclusion remains a difficult one at higher education institutions. Information services provided by academic libraries can result in the digital exclusion of students from diverse backgrounds, such as students with various digital readiness levels, students with disabilities, as well as English-as-a-Second-Language learners. This research study shows how academic librarians can design digital learning objects that are cognizant of differences in learner traits and student profiles through the lens of design thinking. By demonstrating how the design process of digital learning objects can take into consideration users’ needs, experiences, and engagement with different technologies, this research study explains design principles of accessibility, connectivity, and scalability in creating inclusive digital learning objects as shown in various case studies. Equipped with the mindset and techniques to be mindful of diverse student learning traits and profiles when designing information services, academic libraries can improve the digital inclusion and ultimately student success at higher education institutions.

Keywords: academic librarians, digital inclusion, information services, digital learning objects, student success

Procedia PDF Downloads 210

Authors: A. Mohamed Mydeen, Pallapa Venkataram

Abstract:

The learning process needs to be so pervasive to impart the quality in acquiring the knowledge about a subject by making use of the advancement in the field of information and communication systems. However, pervasive learning paradigms designed so far are system automation types and they lack in factual pervasive realm. Providing factual pervasive realm requires subtle ways of teaching and learning with system intelligence. Augmentation of intelligence with pervasive learning necessitates the most efficient way of representing knowledge for the system in order to give the right learning material to the learner. This paper presents a method of representing knowledge for Pervasive Toolroom Maintenance System (PTMS) in which a learner acquires sublime knowledge about the various kinds of tools kept in the toolroom and also helps for effective maintenance of the toolroom. First, we explicate the generic model of knowledge representation for PTMS. Second, we expound the knowledge representation for specific cases of toolkits in PTMS. We have also presented the conceptual view of knowledge representation using ontology for both generic and specific cases. Third, we have devised the relations for pervasive knowledge in PTMS. Finally, events are identified in PTMS which are then linked with pervasive data of toolkits based on relation formulated. The experimental environment and case studies show the accuracy and efficient knowledge representation of toolkits in PTMS.

Keywords: knowledge representation, pervasive computing, agent technology, ECA rules

Procedia PDF Downloads 328

Authors: Şirin Küçük, Ayşe Kök, İsmail Şahin

Abstract:

Mobile devices are very popular and useful tools for assisting people in daily life. With the advancement of mobile technologies, the issue of mobile learning has been widely investigated in education. Many researches consider that it is important to integrate pedagogical and technical strengths of mobile technology into learning environments. For this reason, the purpose of this research is to examine the effect of mobile technology use in education with meta-analysis method. Meta-analysis is a statistical technique which combines the findings of independent studies in a specific subject. In this respect, the articles will be examined by searching the databases for researches which are conducted between 2005 and 2014. It is expected that the results of this research will contribute to future research related to mobile technology use in education.

Keywords: mobile learning, meta-analysis, mobile technology, education

Procedia PDF Downloads 718

Authors: Andrew Nowlan

Abstract:

During the Coronavirus pandemic, collaborative online international learning (COIL) emerged as an alternative to overseas sojourns. However, now that face-to-face classes have resumed and students are studying abroad, the rationale for doing COIL is not always clear amongst educators and students. Also, the logistics of COIL become increasingly complicated when participants involved in a potential collaboration have different second language (L2) learning goals. In this paper, the researcher will report on a study involving two bilingual, cross-cultural COIL courses between students at a university in Japan and those studying in North America, from April to December, 2022. The students in Japan were enrolled in an intercultural communication class in their L2 of English, while the students in Canada and the United States were studying intermediate Japanese as their L2. Based on a qualitative survey and journaling data received from 31 students in Japan, and employing a transcendental phenomenological research design, the researcher will highlight the students’ essence of experience during COIL. Essentially, students benefited from the experience through improved communicative competences and increased knowledge of the target culture, even when the L2 learning goals between institutions differed. Students also reported that the COIL experience was effective in preparation for actual study abroad, as opposed to a replacement for it, which challenges the existing literature. Both educators and administrators will be exposed to the perceptions of Japanese university students towards COIL, which could be generalized to other higher education contexts, including those in Southeast Asia. Readers will also be exposed to ideas for developing more effective pre-departure study abroad programs and domestic intercultural curriculum through COIL, even when L2 learning goals may differ between participants.

Keywords: collaborative online international learning, study abroad, phenomenology, EdTech, intercultural communication

Procedia PDF Downloads 79

Authors: Catherine Omole

Abstract:

Examination malpractice includes acts that temper with collecting accurate results during the conduct of an examination, thereby giving undue advantage to a student over his colleagues. Even though examination malpractice has been a lingering problem, examinations may not be easy to do away with completely as it is an important feedback tool in the learning process with several other functions e.g for the purpose of selection, placement, certification and promotion. Examination malpractice has created a lot of problems such as a relying on a weak work force based on false assessment results. The question is why is this problem still persisting, despite measures that have been taken to curb this ugly trend over the years? This opinion paper has identified modifications that could help relieve the student of the examination stress and thus increase the student’s effort towards effective learning and discourage examination malpractice in the long run.

Keywords: assessment, examination malpractice, learning, science classroom

Procedia PDF Downloads 254

Authors: Jia Li, Xing Wei, Yuchen Hong, Yang Lu

Abstract:

Detecting vehicle behavior has always been the focus of intelligent transportation, but with the explosive growth of the number of vehicles and the complexity of the road environment, the vehicle behavior videos captured by traditional surveillance have been unable to satisfy the study of vehicle behavior. The traditional method of manually labeling vehicle behavior is too time-consuming and labor-intensive, but the existing object detection and tracking algorithms have poor practicability and low behavioral location detection rate. This paper proposes a vehicle behavior detection algorithm based on the dual-stream convolution network and the multi-dimensional video dynamic detection network. In the videos, the straight-line behavior of the vehicle will default to the background behavior. The Changing lanes, turning and turning around are set as target behaviors. The purpose of this model is to automatically mark the target behavior of the vehicle from the untrimmed videos. First, the target behavior proposals in the long video are extracted through the dual-stream convolution network. The model uses a dual-stream convolutional network to generate a one-dimensional action score waveform, and then extract segments with scores above a given threshold M into preliminary vehicle behavior proposals. Second, the preliminary proposals are pruned and identified using the multi-dimensional video dynamic detection network. Referring to the hierarchical reinforcement learning, the multi-dimensional network includes a Timer module and a Spacer module, where the Timer module mines time information in the video stream and the Spacer module extracts spatial information in the video frame. The Timer and Spacer module are implemented by Long Short-Term Memory (LSTM) and start from an all-zero hidden state. The Timer module uses the Transformer mechanism to extract timing information from the video stream and extract features by linear mapping and other methods. Finally, the model fuses time information and spatial information and obtains the location and category of the behavior through the softmax layer. This paper uses recall and precision to measure the performance of the model. Extensive experiments show that based on the dataset of this paper, the proposed model has obvious advantages compared with the existing state-of-the-art behavior detection algorithms. When the Time Intersection over Union (TIoU) threshold is 0.5, the Average-Precision (MP) reaches 36.3% (the MP of baselines is 21.5%). In summary, this paper proposes a vehicle behavior detection model based on multi-dimensional dynamic detection network. This paper introduces spatial information and temporal information to extract vehicle behaviors in long videos. Experiments show that the proposed algorithm is advanced and accurate in-vehicle timing behavior detection. In the future, the focus will be on simultaneously detecting the timing behavior of multiple vehicles in complex traffic scenes (such as a busy street) while ensuring accuracy.

Keywords: vehicle behavior detection, convolutional neural network, long short-term memory, deep learning

Procedia PDF Downloads 125

Authors: Szymon Rutkowski, Tomasz Korbak

Abstract:

We present a reinforcement-learning-based method of training neural machine translation models without parallel corpora. The standard encoder-decoder approach to machine translation suffers from two problems we aim to address. First, it needs parallel corpora, which are scarce, especially for low-resource languages. Second, it lacks psychological plausibility of learning procedure: learning a foreign language is about learning to communicate useful information, not merely learning to transduce from one language’s 'encoding' to another. We instead pose the problem of learning to translate as learning a policy in a communication game between two agents: the translator and the classifier. The classifier is trained beforehand on a natural language inference task (determining the entailment relation between a premise and a hypothesis) in the target language. The translator produces a sequence of actions that correspond to generating translations of both the hypothesis and premise, which are then passed to the classifier. The translator is rewarded for classifier’s performance on determining entailment between sentences translated by the translator to disciple’s native language. Translator’s performance thus reflects its ability to communicate useful information to the classifier. In effect, we train a machine translation model without the need for parallel corpora altogether. While similar reinforcement learning formulations for zero-shot translation were proposed before, there is a number of improvements we introduce. While prior research aimed at grounding the translation task in the physical world by evaluating agents on an image captioning task, we found that using a linguistic task is more sample-efficient. Natural language inference (also known as recognizing textual entailment) captures semantic properties of sentence pairs that are poorly correlated with semantic similarity, thus enforcing basic understanding of the role played by compositionality. It has been shown that models trained recognizing textual entailment produce high-quality general-purpose sentence embeddings transferrable to other tasks. We use stanford natural language inference (SNLI) dataset as well as its analogous datasets for French (XNLI) and Polish (CDSCorpus). Textual entailment corpora can be obtained relatively easily for any language, which makes our approach more extensible to low-resource languages than traditional approaches based on parallel corpora. We evaluated a number of reinforcement learning algorithms (including policy gradients and actor-critic) to solve the problem of translator’s policy optimization and found that our attempts yield some promising improvements over previous approaches to reinforcement-learning based zero-shot machine translation.

Keywords: agent-based language learning, low-resource translation, natural language inference, neural machine translation, reinforcement learning

Procedia PDF Downloads 125

Authors: Hyunbin Choi, Jihyeon Noh, Changwon Lim

Abstract:

In this paper, we propose SiamMask++, an architecture that performs layer-wise aggregation and depth-wise cross-correlation and introduce multi-RPN module and multi-MASK module to improve EAO (Expected Average Overlap), a representative performance evaluation metric for Visual Object Tracking (VOT) challenge. The proposed architecture, SiamMask++, has two versions, namely, bi_SiamMask++, which satisfies the real time (56fps) on systems equipped with GPUs (Titan XP), and rf_SiamMask++, which combines mask refinement modules for EAO improvements. Tests are performed on VOT2016, VOT2018 and VOT2019, the representative datasets of Visual Object Tracking tasks labeled as rotated bounding boxes. SiamMask++ perform better than SiamMask on all the three datasets tested. SiamMask++ is achieved performance of 62.6% accuracy, 26.2% robustness and 39.8% EAO, especially on the VOT2018 dataset. Compared to SiamMask, this is an improvement of 4.18%, 37.17%, 23.99%, respectively. In addition, we do an experimental in-depth analysis of how much the introduction of features and multi modules extracted from the backbone affects the performance of our model in the VOT task.

Keywords: visual object tracking, video, deep learning, layer wise aggregation, Siamese network

Procedia PDF Downloads 148

Authors: Gertrude Nkechi Okenwa

Abstract:

Higher institutions, especially the universities that are saddled with the responsibilities of teaching, learning, research, publications and social services for the production of graduates that are worthy in learning and character, and the creation of up-to-date knowledge and innovations for the total socio-economic and even political development of a given nation. Therefore, the purpose of the study was to identify the teaching, learning techniques used in the Enugu State University of Science and Technology to ensure or ascertain students’ perception on these techniques. To guide the study, survey research method was used. The population for the study was made up of second and final year students which summed up to one hundred and twenty-six students in the faculty of education. Stratified random sampling technique was adopted. A sample size of sixty (60) students was drawn for the study. The instrument used for data collection was questionnaire. To analyze the data, mean and standard deviation were used to answers the research questions. The findings revealed that direct instruction and construction techniques are used in the university. On the whole, it was observed that the students perceived constructivist techniques to be more useful and effective than direct instruction technique. Based on the findings recommendations were made to include diversification of teaching techniques among others.

Keywords: Strategies, Teaching and Learning, Constructive Technique, Direct Instructional Technique

Procedia PDF Downloads 536

Authors: Sefik Can Karakaya, Ibrahim Demir

Abstract:

In this study, the relationship between musical preferences and personality traits has been investigated in terms of Spotify audio analysis features. The aim of this paper is to build such a classifier capable of segmenting people into their Myers-Briggs Type Index (MBTI) personality type based on their Spotify playlists. Music takes an important place in the lives of people all over the world and online music streaming platforms make it easier to reach musical contents. In this context, the motivation to build such a classifier is allowing people to gain access to their MBTI personality type and perhaps for more reliably and more quickly. For this purpose, logistic regression and deep neural networks have been selected for classifier and their performances are compared. In conclusion, it has been found that musical preferences differ statistically between personality traits, and evaluated models are able to distinguish personality types based on given musical data structure with over %60 accuracy rate.

Keywords: myers-briggs type indicator, music psychology, Spotify, behavioural user profiling, deep neural networks, logistic regression

Procedia PDF Downloads 137

Authors: Sobhy Fathy A. Hashesh

Abstract:

The study was carried out in the Elementary Classes of Andalus Private Schools, girls section using control and experimental groups formed by Random Assignment Strategy. The study aimed at investigating the effect of Al-Andalus Fused Curriculum (AFC) model of learning and the effect of separate subjects’ approach on the development of students’ conceptual learning and skills acquiring. The society of the study composed of Al-Andalus Private Schools, elementary school students, Girls Section (N=240), while the sample of the study composed of two randomly assigned groups (N=28) with one experimental group and one control group. The study followed the quantitative and qualitative approaches in collecting and analyzing data to investigate the study hypotheses. Results of the study revealed that there were significant statistical differences between students’ conceptual learning and skills acquiring for the favor of the experimental group. The study recommended applying this model on different educational variables and on other age groups to generate more data leading to more educational results for the favor of students’ learning outcomes.

Keywords: AFC, STEAM, lego education, Al-Andalus fused curriculum, mechatronics

Procedia PDF Downloads 214

Authors: Daniel A. Walzer

Abstract:

As the options for course delivery and development expand, plenty of misconceptions still exist concerning e-learning and online course delivery. Classroom instructors often discuss pedagogy, methodologies, and best practices regarding teaching from a singular, traditional in-class perspective. As more professors integrate online, blended, and hybrid courses into their dossier, a clearly defined rubric for gauging online course delivery is essential. The transition from a traditional learning structure towards an updated distance-based format requires careful planning, evaluation, and revision. This paper examines how new media stimulates reflective practice and guided inquiry to improve pedagogy, engage interdisciplinary collaboration, and supply rich qualitative data for future research projects in media arts disciplines.

Keywords: action research, inquiry, new media, reflection

Procedia PDF Downloads 305

Authors: Jenny Hall, Alison Jaquet

Abstract:

Universities’ push toward the production of high quality research is not limited to academic staff and experienced researchers. In this environment of research rich agendas, Higher Degree Research (HDR) students are increasingly expected to engage in the publishing of good quality papers in high impact journals. IFN001: Advanced Information Research Skills (AIRS) is a credit bearing mandatory coursework requirement for Queensland University of Technology (QUT) doctorates. Since its inception in 1989, this unique blended learning program has provided the foundations for new researchers to produce original and innovative research. AIRS was redeveloped in 2012, and has now been evaluated with reference to the university’s strategic research priorities. Our research is the first comprehensive evaluation of the program from the learner perspective. We measured whether the program develops essential transferrable skills and graduate capabilities to ensure best practice in the areas of publishing and data management. In particular, we explored whether AIRS prepares students to be agile researchers with the skills to adapt to different research contexts both within and outside academia. The target group for our study consisted of HDR students and supervisors at QUT. Both quantitative and qualitative research methods were used for data collection. Gathering data was by survey and focus groups with qualitative responses analyzed using NVivo. The results of the survey show that 82% of students surveyed believe that AIRS assisted their research process and helped them learn skills they need as a researcher. The 18% of respondents who expressed reservation about the benefits of AIRS were also examined to determine the key areas of concern. These included trends related to the timing of the program early in the candidature and a belief among some students that their previous research experience was sufficient for postgraduate study. New insights have been gained into how to better support HDR learners in partnership with supervisors and how to enhance learning experiences of specific cohorts, including international students and mature learners.

Keywords: data management, enhancing learning experience, publishing, research higher degree students, doctoral students

Procedia PDF Downloads 273

Authors: Karthik Mittal

Abstract:

This study performs an unsupervised machine learning analysis to find clusters of related SNPs which highlight biological pathways that are important for the biological mechanisms of breast cancer. Studying genetic variations in isolation is illogical because these genetic variations are known to modulate protein production and function; the downstream effects of these modifications on biological outcomes are highly interconnected. After extracting the SNPs and their effect on different types of breast cancer using the MRBase library, two unsupervised machine learning clustering algorithms were implemented on the genetic variants: a k-means clustering algorithm and a hierarchical clustering algorithm; furthermore, principal component analysis was executed to visually represent the data. These algorithms specifically used the SNP’s beta value on the three different types of breast cancer tested in this project (estrogen-receptor positive breast cancer, estrogen-receptor negative breast cancer, and breast cancer in general) to perform this clustering. Two significant genetic pathways validated the clustering produced by this project: the MAPK signaling pathway and the connection between the BRCA2 gene and the ESR1 gene. This study provides the first proof of concept showing the importance of unsupervised machine learning in interpreting GWAS summary statistics.

Keywords: breast cancer, computational biology, unsupervised machine learning, k-means, PCA

Procedia PDF Downloads 138

Authors: Naira Poghosyan

Abstract:

In knowledge society the content of the studies, the methods used and the requirements for an educator’s professionalism regularly undergo certain changes. It follows that in knowledge society the aim of education is not only to educate professionals for a certain field but also to help students to be aware of cultural values, form human mutual relationship, collaborate, be open, adapt to the new situation, creatively express their ideas, accept responsibility and challenge. In this viewpoint, the development of communicative language competence requires a through coordinated approach to ensure proper comprehension and memorization of subject-specific words starting from high school level. On the other hand, ESP (English for Specific Purposes) teachers and practitioners are increasingly faced with the task of developing and exploiting new ways of assessing their learners’ literacy while learning and teaching ESP. The presentation will highlight the latest achievements in this field. The author will present some practical methodological issues and principles associated with learning, teaching and assessing ESP skills of the learners, using the two software programs of EXE 2.0 and Hot Potatoes 6. On the one hand the author will display the advantages of the two programs as self-learning and self-assessment interactive tools in the course of academic study and professional development of the CLIL learners, on the other hand, she will comprehensively shed light upon some methodological aspects of working out appropriate ways of selection, introduction, consolidation of subject specific materials via EXE 2.0 and Hot Potatoes 6. Then the author will go further to distinguish ESP courses by the general nature of the learners’ specialty identifying three large categories of EST (English for Science and Technology), EBE (English for Business and Economics) and ESS (English for the Social Sciences). The cornerstone of the presentation will be the introduction of the subject titled “The methodology of teaching ESP in non-linguistic institutions”, where a unique case of teaching ESP on Architecture and Construction via EXE 2.0 and Hot Potatoes 6 will be introduced, exemplifying how the introduction, consolidation and assessment can be used as a basis for feedback to the ESP learners in a particular professional field.

Keywords: ESP competences, ESP skill assessment/ self-assessment tool, eXe 2.0 / HotPotatoes software program, ESP teaching strategies and techniques

Procedia PDF Downloads 374

Authors: Anam Gopi

Abstract:

The undesired torque and flux ripple may occur in conventional direct torque control (DTC) induction motor drive. DTC can improve the system performance at low speeds by continuously tuning the regulator by adjusting the Kp, Ki values. In this Teaching Learning Based Optimization (TLBO) is proposed to adjust the parameters (Kp, Ki) of the speed controller in order to minimize torque ripple, flux ripple, and stator current distortion. The TLBO based PI controller has resulted is maintaining a constant speed of the motor irrespective of the load torque fluctuations.

Keywords: teaching learning based optimization, direct torque control, PI controller

Procedia PDF Downloads 582

Authors: Agis Andriani

Abstract:

To create an effective teaching condition, the teacher requests the students as the instruction to guide the them interactively in the learning activities in the classroom. This study involves 160 Indonesian students who study English in the university, as participants in the discourse completion test, and ten of them are interviewed. The result shows that when the students response the teacher’s request, it realizes assertives, directives, commisives, expressives, and declaratives. These indicate that the students are active, motivated, and responsive in the learning process, although in the certain condition these responses are to prevent their faces from the shyness of their silence in interaction. Therefore, it needs the teacher’s creativity to give the conducive atmosphere in order to support the students’ participation in learning English.

Keywords: discourse completion test, effective teaching, request, teacher’s creativity

Procedia PDF Downloads 428

Authors: Ágoston Nagy

Abstract:

This paper introduces a method of using unsupervised machine learning to visualize the feature space of a dataset in 2D, in order to find most characteristic segments in the set. After dimension reduction, users can select clusters by manual drawing. Selected clusters are recorded into a data model that is used for later predictions, based on realtime data. Predictions are made with supervised learning, using Gesture Recognition Toolkit. The paper introduces two example applications: a semantic audio organizer for analyzing incoming sounds, and a gesture database organizer where gestural data (recorded by a Leap motion) is visualized for further manipulation.

Keywords: gesture recognition, machine learning, real-time interaction, visualization

Procedia PDF Downloads 348

Authors: Tesfaye Mengistu

Abstract:

This thesis aims to investigate the effectiveness of Reinforcement Learning (RL) for Autonomous Energy Management solutions. The study explores the potential of Model Free RL approaches, such as Monte Carlo RL and Q-learning, to improve energy management by autonomously adjusting energy management strategies to maximize efficiency. The research investigates the implementation of RL algorithms for optimizing energy consumption in a single-agent environment. The focus is on developing a framework for the implementation of RL algorithms, highlighting the importance of RL for enabling autonomous systems to adapt quickly to changing conditions and make decisions based on previous experiences. Moreover, the paper proposes RL as a novel energy management solution to address nations' CO2 emission goals. Reinforcement learning algorithms are well-suited to solving problems with sequential decision-making patterns and can provide accurate and immediate outputs to ease the planning and decision-making process. This research provides insights into the challenges and opportunities of using RL for energy management solutions and recommends further studies to explore its full potential. In conclusion, this study provides valuable insights into how RL can be used to improve the efficiency of energy management systems and supports the use of RL as a promising approach for developing autonomous energy management solutions in residential buildings.

Keywords: artificial intelligence, reinforcement learning, monte carlo, energy management, CO2 emission

Procedia PDF Downloads 77

Authors: Malathi Balakrishnan, Cheng Lee Ooi, Chander Vengadasalam

Abstract:

The purpose of this study is to explore a case study of trainee teachers’ learning experience on innovating traditional games during the traditional game carnival. It explores issues arising from multiple case studies of trainee teachers learning experiences in innovating traditional games. A qualitative methodology was adopted through observations, semi-structured interviews and reflective journals’ content analysis of trainee teachers’ learning experiences creating and implementing innovative traditional games. Twelve groups of 36 trainee teachers who registered for Sports and Physical Education Management Course were the participants for this research during the traditional game carnival. Semi structured interviews were administrated after the trainee teachers learning experiences in creating innovative traditional games. Reflective journals were collected after carnival day and the content analyzed. Inductive data analysis was used to evaluate various data sources. All the collected data were then evaluated through the Nvivo data analysis process. Inductive reasoning was interpreted based on the Self Determination Theory (SDT). The findings showed that the trainee teachers had positive game participation experiences, game knowledge about traditional games and positive motivation to innovate the game. The data also revealed the influence of themes like cultural significance and creativity. It can be concluded from the findings that the organized game carnival, as a requirement of course work by the Institute of Teacher Training Malaysia, was able to enhance teacher trainers’ innovative thinking skills. The SDT, as a multidimensional approach to motivation, was utilized. Therefore, teacher trainers may have more learning experiences using the SDT.

Keywords: learning experiences, innovation, traditional games, trainee teachers

Procedia PDF Downloads 328

Authors: Ira Slabodar

Abstract:

Autonomous learning in English as a Foreign Language (EFL) refers to the use of target language, learner collaboration and students’ responsibility for their learning. Teachers play a vital role of mediators and facilitators in self-regulated method. Thus, their perception of self-guided practices dictates their implementation of this approach. While research has predominantly focused on inadequate administration of autonomous learning in school mostly due to lack of appropriate teacher training, this study examined whether novice teachers who were exposed to extensive autonomous practices were likely to implement this method in their teaching. Twelve novice teachers were interviewed to examine their perception of learner autonomy and their administration of this method. It was found that three-thirds of the respondents experienced a gap between familiarity with autonomous learning and a favorable attitude to this approach and their deficient integration of self-directed learning. Although learner-related and institution-oriented factors played a role in this gap, it was mostly caused by the respondents’ not being genuinely autonomous. This may be due to indirect exposure rather than explicit introduction of the learner autonomy approach. The insights of this research may assist curriculum designers and heads of teacher training programs to rethink course composition to guarantee the transfer of methodologies into EFL classes.

Keywords: learner autonomy, teacher training, english as a foreign language (efl), genuinely autonomous teachers, explicit instruction, self-determination theory

Procedia PDF Downloads 54

Authors: Chan Ka Lok Sobel

Abstract:

The rapid evolution of digital media platforms has given rise to new forms of narrative engagement, particularly through multi-channel storytelling. This research focuses on exploring the teaching pedagogy and effectiveness of multi-channel storytelling for social media, cinema, games, and streaming platforms. The study employs case studies of the popular series "Squid Game" to investigate the diverse pedagogical approaches and strategies used in teaching multi-channel storytelling. Through qualitative research methods, including interviews, surveys, and content analysis, the research assesses the effectiveness of these approaches in terms of student engagement, knowledge acquisition, critical thinking skills, and the development of digital literacy. The findings contribute to understanding best practices for incorporating multi-channel storytelling into educational contexts and enhancing learning outcomes in the digital media landscape.

Keywords: digital literacy, game-based learning, artificial intelligence, animation production, educational technology

Procedia PDF Downloads 104

Authors: A. Soni, D. R. Mishra, D. K. Koul

Abstract:

α-Al2O3:C has been reported to have deeper traps at 600°C and 900°C respectively. These traps have been reported to accessed at relatively earlier temperatures (122 and 322 °C respectively) using thermally assisted OSL (TA-OSL). In this work, the dose response α-Al2O3:C was studied in the dose range of 10Gy to 10kGy for its application in food irradiation in low ( upto 1kGy) and medium(1 to 10kGy) dose range. The TOL (Thermo-optically stimulated luminescence) measurements were carried out on RisØ TL/OSL, TL-DA-15 system having a blue light-emitting diodes (λ=470 ±30nm) stimulation source with power level set at the 90% of the maximum stimulation intensity for the blue LEDs (40 mW/cm2). The observations were carried on commercial α-Al2O3:C phosphor. The TOL experiments were carried out with number of active channel (300) and inactive channel (1). Using these settings, the sample is subjected to linear thermal heating and constant optical stimulation. The detection filter used in all observations was a Hoya U-340 (Ip ~ 340 nm, FWHM ~ 80 nm). Irradiation of the samples was carried out using a 90Sr/90Y β-source housed in the system. A heating rate of 2 °C/s was preferred in TL measurements so as to reduce the temperature lag between the heater plate and the samples. To study the dose response of deep traps of α-Al2O3:C, samples were irradiated with various dose ranging from 10 Gy to 10 kGy. For each set of dose, three samples were irradiated. In order to record the TA-OSL, initially TL was recorded up to a temperature of 400°C, to deplete the signal due to 185°C main dosimetry TL peak in α-Al2O3:C, which is also associated with the basic OSL traps. After taking TL readout, the sample was subsequently subjected to TOL measurement. As a result, two well-defined TA-OSL peaks at 121°C and at 232°C occur in time as well as temperature domain which are different from the main dosimetric TL peak which occurs at ~ 185°C. The linearity of the integrated TOL signal has been measured as a function of absorbed dose and found to be linear upto 10kGy. Thus, it can be used for low and intermediate dose range of for its application in food irradiation. The deep energy level defects of α-Al2O3:C phosphor can be accessed using TOL section of RisØ reader system.

Keywords: α-Al2O3:C, deep traps, food irradiation, TA-OSL

Procedia PDF Downloads 293

Authors: Gila Kurtz, Dan Kohen Vacs

Abstract:

Social robots (SR) is an emerging field striving to deploy computers capable of resembling human shapes and mimicking human movements, gestures, and behaviors. The evolving capability of SR to interact with human offers groundbreaking ways for learning and training opportunities. Studies show that SR can offer instructional experiences for fostering creativity, entertainment, enjoyment, and curiosity. These added values are essential for empowering instructional opportunities as gamified learning experiences. We present our project focused on deploying an activity to be experienced in an escape room aimed at team-based learning scaffolded by an SR, NAO. An escape room is a well-known approach for gamified activities focused on a simulated scenario experienced by team-based participants. Usually, the simulation takes place in a physical environment where participants must complete a series of challenges in a limited amount of time. During this experience, players learn something about the assigned topic of the room. In the current learning simulation, students must "save the nation" by locating sensitive information stolen and stored in a vault of four locks. Team members have to look for hints and solve riddles mediated by NAO. Each solution provides a unique code for opening one of the four locks. NAO is also used to provide ongoing feedback on the team's performance. We captured the proceeding of our activity and used it to conduct an evaluation study among ten experts in related areas. The experts were interviewed on their overall assessment of the learning activity and their perception of the added value related to the robot. The results were very encouraging on the feasibility that NAO can serve as a motivational tutor in adults' collaborative game-based learning. We believe that this study marks the first step toward a template for developing innovative team-based training using escape rooms supported by a humanoid robot.

Keywords: social robot, NAO, learning, team based activity, escape room

Procedia PDF Downloads 66

Authors: Ahlem Abid, Farah Jemili

Abstract:

Intrusion detection has been the subject of numerous studies in industry and academia, but cyber security analysts always want greater precision and global threat analysis to secure their systems in cyberspace. To improve intrusion detection system, the visualisation of the security events in form of graphs and diagrams is important to improve the accuracy of alerts. In this paper, we propose an approach of an IDS based on cloud computing, big data technique and using a machine learning graph algorithm which can detect in real time different attacks as early as possible. We use the MAWILab intrusion detection dataset . We choose Microsoft Azure as a unified cloud environment to load our dataset on. We implement the k2 algorithm which is a graphical machine learning algorithm to classify attacks. Our system showed a good performance due to the graphical machine learning algorithm and spark structured streaming engine.

Keywords: Apache Spark Streaming, Graph, Intrusion detection, k2 algorithm, Machine Learning, MAWILab, Microsoft Azure Cloud

Procedia PDF Downloads 141

Authors: Haohao Wang

Abstract:

Technology, multimedia in Open Educational Resources, can contribute positively to student performance in an online instructional environment. Student performance data of past four years were obtained from an online course entitled Applied Calculus (MA139). This paper examined the data to determine whether multimedia (independent variable) had any impact on student performance (dependent variable) in online math learning, and how students felt about the value of the technology. Two groups of student data were analyzed, group 1 (control) from the online applied calculus course that did not use multimedia instructional materials, and group 2 (treatment) of the same online applied calculus course that used multimedia instructional materials. For the MA139 class, results indicate a statistically significant difference (p = .001) between the two groups, where group 1 had a final score mean of 56.36 (out of 100), group 2 of 70.68. Additionally, student testimonials were discussed in which students shared their experience in learning applied calculus online with multimedia instructional materials.

Keywords: online learning, open educational resources, multimedia, technology

Procedia PDF Downloads 369

Authors: Tanit Pruktara

Abstract:

The research aimed to study the students’ learning achievement and awareness level on electrical energy consumption and conservation and also to investigate the students’ attitude on the developed multimedia supplemented instructional unit for learning household electrical energy consumption and conservation in grade 10 Thailand student. This study used a quantitative method using MCQ for pre and post-achievement tests and Likert scales for awareness and attitude survey questionnaires. The results from this were employed to improve the multimedia to be appropriate for the classroom and with real life situations in the second phase, the main study. The experimental results showed that the developed learning unit significantly improved the students’ learning achievement as well as their awareness of electric energy conservation. Additional we found the student will enjoy participating in class activities when the lessons are taught using multimedia and helps them to develop the relevance between the course and real world situations.

Keywords: lesson plan, media and animations, training course, vocational school in Thailand

Procedia PDF Downloads 171